diff options
| author | Nadav Rotem <nrotem@apple.com> | 2012-10-25 00:08:41 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2012-10-25 00:08:41 +0000 |
| commit | 8dbac7b529cfb73bcd0ceef514e5c1d247cf3baa (patch) | |
| tree | f218f4a19b353a97d10da19af5872eb25d8a452c /test | |
| parent | 3c5e22db7ac9763b376626f1126136e51fba6577 (diff) | |
| download | llvm-8dbac7b529cfb73bcd0ceef514e5c1d247cf3baa.tar.gz llvm-8dbac7b529cfb73bcd0ceef514e5c1d247cf3baa.tar.bz2 llvm-8dbac7b529cfb73bcd0ceef514e5c1d247cf3baa.tar.xz | |
Add support for additional reduction variables: AND, OR, XOR.
Patch by Paul Redmond <paul.redmond@intel.com>.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166649 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
| -rw-r--r-- | test/Transforms/LoopVectorize/reduction.ll | 79 |
1 files changed, 79 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/reduction.ll b/test/Transforms/LoopVectorize/reduction.ll index ca51c7b37d..746a08c3ea 100644 --- a/test/Transforms/LoopVectorize/reduction.ll +++ b/test/Transforms/LoopVectorize/reduction.ll @@ -149,4 +149,83 @@ for.end: ; preds = %for.body, %entry ret i32 %sum.0.lcssa } +;CHECK: @reduction_and +;CHECK: and <4 x i32> +;CHECK: ret i32 +define i32 @reduction_and(i32 %n, i32* nocapture %A, i32* nocapture %B) nounwind uwtable readonly { +entry: + %cmp7 = icmp sgt i32 %n, 0 + br i1 %cmp7, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %result.08 = phi i32 [ %and, %for.body ], [ -1, %entry ] + %arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %arrayidx2 = getelementptr inbounds i32* %B, i64 %indvars.iv + %1 = load i32* %arrayidx2, align 4 + %add = add nsw i32 %1, %0 + %and = and i32 %add, %result.08 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body +for.end: ; preds = %for.body, %entry + %result.0.lcssa = phi i32 [ -1, %entry ], [ %and, %for.body ] + ret i32 %result.0.lcssa +} + +;CHECK: @reduction_or +;CHECK: or <4 x i32> +;CHECK: ret i32 +define i32 @reduction_or(i32 %n, i32* nocapture %A, i32* nocapture %B) nounwind uwtable readonly { +entry: + %cmp7 = icmp sgt i32 %n, 0 + br i1 %cmp7, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %result.08 = phi i32 [ %or, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %arrayidx2 = getelementptr inbounds i32* %B, i64 %indvars.iv + %1 = load i32* %arrayidx2, align 4 + %add = add nsw i32 %1, %0 + %or = or i32 %add, %result.08 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + %result.0.lcssa = phi i32 [ 0, %entry ], [ %or, %for.body ] + ret i32 %result.0.lcssa +} + +;CHECK: @reduction_xor +;CHECK: xor <4 x i32> +;CHECK: ret i32 +define i32 @reduction_xor(i32 %n, i32* nocapture %A, i32* nocapture %B) nounwind uwtable readonly { +entry: + %cmp7 = icmp sgt i32 %n, 0 + br i1 %cmp7, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %result.08 = phi i32 [ %xor, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %arrayidx2 = getelementptr inbounds i32* %B, i64 %indvars.iv + %1 = load i32* %arrayidx2, align 4 + %add = add nsw i32 %1, %0 + %xor = xor i32 %add, %result.08 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + %result.0.lcssa = phi i32 [ 0, %entry ], [ %xor, %for.body ] + ret i32 %result.0.lcssa +} |